From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
commit 16ffa12d742534d4ff73e8b3a4e81c1de39196f0 upstream.
There's a number of 'interesting' problems, all caused by holding
hb->lock while doing the rt_mutex_unlock() equivalient.
Notably:
- a PI inversion on hb->lock; and,
- a SCHED_DEADLINE crash because of pointer instability.
The previous changes:
- changed the locking rules to cover {uval,pi_state} with wait_lock.
- allow to do rt_mutex_futex_unlock() without dropping wait_lock; which in
turn allows to rely on wait_lock atomicity completely.
- simplified the waiter conundrum.
It's now sufficient to hold rtmutex::wait_lock and a reference on the
pi_state to protect the state consistency, so hb->lock can be dropped
before calling rt_mutex_futex_unlock().
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: juri.lelli@xxxxxxx
Cc: bigeasy@xxxxxxxxxxxxx
Cc: xlpang@xxxxxxxxxx
Cc: rostedt@xxxxxxxxxxx
Cc: mathieu.desnoyers@xxxxxxxxxxxx
Cc: jdesfossez@xxxxxxxxxxxx
Cc: dvhart@xxxxxxxxxxxxx
Cc: bristot@xxxxxxxxxx
Link: http://lkml.kernel.org/r/20170322104151.900002056@xxxxxxxxxxxxx
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
[bwh: Backported to 4.9: adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
kernel/futex.c | 111 ++++++++++++++++++++++++++++++-------------------
1 file changed, 68 insertions(+), 43 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c
index bf410a4fab71..c8ec4e7f3609 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -966,10 +966,12 @@ static void exit_pi_state_list(struct task_struct *curr)
pi_state->owner = NULL;
raw_spin_unlock_irq(&curr->pi_lock);
- rt_mutex_futex_unlock(&pi_state->pi_mutex);
-
+ get_pi_state(pi_state);
spin_unlock(&hb->lock);
+ rt_mutex_futex_unlock(&pi_state->pi_mutex);
+ put_pi_state(pi_state);
+
raw_spin_lock_irq(&curr->pi_lock);
}
raw_spin_unlock_irq(&curr->pi_lock);
@@ -1083,6 +1085,11 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
* has dropped the hb->lock in between queue_me() and unqueue_me_pi(),
* which in turn means that futex_lock_pi() still has a reference on
* our pi_state.
+ *
+ * The waiter holding a reference on @pi_state also protects against
+ * the unlocked put_pi_state() in futex_unlock_pi(), futex_lock_pi()
+ * and futex_wait_requeue_pi() as it cannot go to 0 and consequently
+ * free pi_state before we can take a reference ourselves.
*/
WARN_ON(!atomic_read(&pi_state->refcount));
@@ -1537,48 +1544,40 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
q->lock_ptr = NULL;
}
-static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *top_waiter,
- struct futex_hash_bucket *hb)
+/*
+ * Caller must hold a reference on @pi_state.
+ */
+static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
{
- struct task_struct *new_owner;
- struct futex_pi_state *pi_state = top_waiter->pi_state;
u32 uninitialized_var(curval), newval;
+ struct task_struct *new_owner;
+ bool deboost = false;
WAKE_Q(wake_q);
- bool deboost;
int ret = 0;
- if (!pi_state)
- return -EINVAL;
-
- /*
- * If current does not own the pi_state then the futex is
- * inconsistent and user space fiddled with the futex value.
- */
- if (pi_state->owner != current)
- return -EINVAL;
-
raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
-
- /*
- * When we interleave with futex_lock_pi() where it does
- * rt_mutex_timed_futex_lock(), we might observe @top_waiter futex_q waiter,
- * but the rt_mutex's wait_list can be empty (either still, or again,
- * depending on which side we land).
- *
- * When this happens, give up our locks and try again, giving the
- * futex_lock_pi() instance time to complete, either by waiting on the
- * rtmutex or removing itself from the futex queue.
- */
if (!new_owner) {
- raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
- return -EAGAIN;
+ /*
+ * Since we held neither hb->lock nor wait_lock when coming
+ * into this function, we could have raced with futex_lock_pi()
+ * such that we might observe @this futex_q waiter, but the
+ * rt_mutex's wait_list can be empty (either still, or again,
+ * depending on which side we land).
+ *
+ * When this happens, give up our locks and try again, giving
+ * the futex_lock_pi() instance time to complete, either by
+ * waiting on the rtmutex or removing itself from the futex
+ * queue.
+ */
+ ret = -EAGAIN;
+ goto out_unlock;
}
/*
- * We pass it to the next owner. The WAITERS bit is always
- * kept enabled while there is PI state around. We cleanup the
- * owner died bit, because we are the owner.
+ * We pass it to the next owner. The WAITERS bit is always kept
+ * enabled while there is PI state around. We cleanup the owner
+ * died bit, because we are the owner.
*/
newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
@@ -1611,15 +1610,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *top_waiter
deboost = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
}
+out_unlock:
raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
- spin_unlock(&hb->lock);
if (deboost) {
wake_up_q(&wake_q);
rt_mutex_adjust_prio(current);
}
- return 0;
+ return ret;
}
/*
@@ -2493,7 +2492,7 @@ static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
if (get_futex_value_locked(&uval, uaddr))
goto handle_fault;
- while (1) {
+ for (;;) {
newval = (uval & FUTEX_OWNER_DIED) | newtid;
if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
@@ -3006,10 +3005,36 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
*/
top_waiter = futex_top_waiter(hb, &key);
if (top_waiter) {
- ret = wake_futex_pi(uaddr, uval, top_waiter, hb);
+ struct futex_pi_state *pi_state = top_waiter->pi_state;
+
+ ret = -EINVAL;
+ if (!pi_state)
+ goto out_unlock;
+
/*
- * In case of success wake_futex_pi dropped the hash
- * bucket lock.
+ * If current does not own the pi_state then the futex is
+ * inconsistent and user space fiddled with the futex value.
+ */
+ if (pi_state->owner != current)
+ goto out_unlock;
+
+ /*
+ * Grab a reference on the pi_state and drop hb->lock.
+ *
+ * The reference ensures pi_state lives, dropping the hb->lock
+ * is tricky.. wake_futex_pi() will take rt_mutex::wait_lock to
+ * close the races against futex_lock_pi(), but in case of
+ * _any_ fail we'll abort and retry the whole deal.
+ */
+ get_pi_state(pi_state);
+ spin_unlock(&hb->lock);
+
+ ret = wake_futex_pi(uaddr, uval, pi_state);
+
+ put_pi_state(pi_state);
+
+ /*
+ * Success, we're done! No tricky corner cases.
*/
if (!ret)
goto out_putkey;
@@ -3024,7 +3049,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
* setting the FUTEX_WAITERS bit. Try again.
*/
if (ret == -EAGAIN) {
- spin_unlock(&hb->lock);
put_futex_key(&key);
goto retry;
}
@@ -3032,7 +3056,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
* wake_futex_pi has detected invalid state. Tell user
* space.
*/
- goto out_unlock;
+ goto out_putkey;
}
/*
@@ -3042,8 +3066,10 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
* preserve the WAITERS bit not the OWNER_DIED one. We are the
* owner.
*/
- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+ spin_unlock(&hb->lock);
goto pi_faulted;
+ }
/*
* If uval has changed, let user space handle it.
@@ -3057,7 +3083,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
return ret;
pi_faulted:
- spin_unlock(&hb->lock);
put_futex_key(&key);
ret = fault_in_user_writeable(uaddr);
Attachment:
signature.asc
Description: PGP signature
